Global ETD Search

1	Supervision : Object motion interpretation using hyperdimensional computing based on object detection run on the edge Andersson Svensson, Albin January 2022 (has links) This thesis demonstrates a technique for developing efficient applications interpreting spacial deep learning output using Hyper Dimensional Computing (HDC), also known as Vector Symbolic Architecture (VSA). As a part of the application demonstration, a novel preprocessing technique for motion using state machines and spacial semantic pointers will be explained. The application will be evaluated and run on a Google Coral edge TPU interpreting real time inference of a compressed object detection model. Machine learning Object detection Motion Interpretation Hyperdimensional Computing Vector Symbolic Architecture Computer Systems Datorsystem Embedded Systems Inbäddad systemteknik Robotics Robotteknik och automation Signal Processing Signalbehandling